ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-06 07:51:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Let it be the multiple number of CU

Browse Source
This commit is contained in:
rocking
2022-05-18 08:38:30 +08:00
parent b7a82d292d
commit 83f7531364
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/tensor_operation/gpu/device/device_binary_elementwise.hpp
View File

@@ -86,7 +86,7 @@ struct DeviceBinaryElementwise : public BaseOperator
p_c_(p_c),
functor_(functor),
threadPerBlock_(threadPerBlock),
gridSize_(128) // FIXME - Calculate the grid size by number of CU in the future
gridSize_(120) // FIXME - Calculate the grid size by number of CU in the future
{
a_grid_desc_m0_ = MakeDescriptor_M0(shape, stride_a, gridSize_, threadPerBlock_);
b_grid_desc_m0_ = MakeDescriptor_M0(shape, stride_b, gridSize_, threadPerBlock_);